일종의

crawling을 할때 requests를 던질때 selenium에서 downloader역할을 한다.

# Define here the models for your spider middleware
#
# See documentation in:
# <https://docs.scrapy.org/en/latest/topics/spider-middleware.html>

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter

class TutorialSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod  # 데코레이터인데이 클래스에서 이 함수를 호출해서 사용가능
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls() # 여기서 cls()는 crawler 을 의미
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        # crawler가 실행될때 spider가 생성되면 middleware의 spider_opened가 실행되록 설정
				return s   #그리고 이 실행된 crawler를 return

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

class TutorialDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

		# response를 받을 때 실행되는 함수
    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

		# 여기서 selenium을 정의, spider가 생성될 때 실행되는함수
    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)